INDEX
Explanations
words and phrases related to food preparation and cooking instructions
New Auto-Interp
Head Attr Weights
0:0.03
1:0.02
2:0.07
3:0.05
4:0.04
5:0.03
6:0.38
7:0.10
8:0.04
9:0.06
10:0.07
11:0.04
Negative Logits
Christy
-1.36
Gina
-1.34
Finger
-1.31
Vij
-1.28
Alphabet
-1.24
Balls
-1.24
Cosponsors
-1.23
Doodle
-1.22
Twice
-1.19
ンジ
-1.19
POSITIVE LOGITS
etheus
1.49
hest
1.39
itans
1.31
maximum
1.31
vec
1.26
death
1.26
cend
1.26
oln
1.25
haust
1.24
naissance
1.23
Activations Density 0.001%